Tag
The paper introduces Lie–Taylor jet matching, a solver-free framework for training Universal Differential Equations on microcontrollers, achieving accuracy comparable to traditional methods with minimal memory usage.
This paper evaluates five model families for macroeconomic forecasting, finding that less-constrained models like ARIMA and Neural ODE outperform structurally-prioritized models like PINNs, highlighting that structural priors can act as misregularizers when mismatched.